INDEX

Explanations

questions and requests for information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etti

-0.16

rvine

-0.15

illon

-0.15

itr

-0.14

 succ

-0.14

 polar

-0.14

ijken

-0.13

ating

-0.13

POSITIVE LOGITS

icap

0.15

(required

0.15

 Disqus

0.15

ë²Į

0.15

ded

0.14

trap

0.14

ÑģÑĤÑĸ

0.14

HOH

0.13

ÑĨÐµÐ²

0.13

dsa

0.13

Activations Density 0.061%

questions and requests for information

No Comments

No Known Activations